Fabio Hellmann

Mr. Fabio Hellmann

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 December 2024 in ACM Transactions on Multimedia Computing, Communications, and Applications
Verified
Journal Article
Open access
FHFabio Hellmann
Fabio Hellmann
SMSilvan Mertes
Silvan Mertes
BMBenouis Mohamed
Benouis Mohamed
AHAlexander Hustinx
Alexander Hustinx
THTzung-Chien Hsieh
Tzung-Chien Hsieh
EAElisabeth André
Elisabeth André
In recent years, the increasing availability of personal data has raised concerns regarding privacy and security. One of the critical processes to address these concerns is data anonymization, which aims to protect individual privacy and prevent the release of sensitive information. This research focuses on the importance of face anonymization. Therefore, we introduce GANonymization, a novel face anonymization framework with facial expression-preserving abilities. Our approach is based on a high-level representation of a face, which is synthesized into an anonymized version based on a generative adversarial network (GAN). The effectiveness of the approach was assessed by evaluating its performance in removing identifiable facial attributes to increase the anonymity of the given individual face. Additionally, the performance of preserving facial expressions was evaluated on several affect recognition datasets and outperformed the state-of-the-art methods in most categories. Finally, our approach was analyzed for its ability to remove various facial traits, such as jewelry, hair color, and multiple others. Here, it demonstrated reliable performance in removing these attributes. Our results suggest that GANonymization is a promising approach for anonymizing faces while preserving facial expressions.

15 January 2025 in European Journal of Human Genetics
Verified
Journal Article
Open access
PDF file
AKAron Kirchhoff
Aron Kirchhoff
AHAlexander Hustinx
Alexander Hustinx
BJBehnam Javanmardi
Behnam Javanmardi
THTzung-Chien Hsieh
Tzung-Chien Hsieh
FBFabian Brand
Fabian Brand
PKPeter Krawitz
Peter Krawitz
The facial gestalt (overall facial morphology) is a characteristic clinical feature in many genetic disorders that is often essential for suspecting and establishing a specific diagnosis. Therefore, publishing images of individuals affected by pathogenic variants in disease-associated genes has been an important part of scientific communication. Furthermore, medical imaging data is also crucial for teaching and training deep-learning models such as GestaltMatcher. However, medical data is often sparsely available, and sharing patient images involves risks related to privacy and re-identification. Therefore, we explored whether generative neural networks can be used to synthesize accurate portraits for rare disorders. We modified a StyleGAN architecture and trained it to produce artificial condition-specific portraits for multiple disorders. In addition, we present a technique that generates a sharp and detailed average patient portrait for a given disorder. We trained our GestaltGAN on the 20 most frequent disorders from the GestaltMatcher database. We used REAL-ESRGAN to increase the resolution of portraits from the training data with low-quality and colorized black-and-white images. To augment the model’s understanding of human facial features, an unaffected class was introduced to the training data. We tested the validity of our generated portraits with 63 human experts. Our findings demonstrate the model’s proficiency in generating photorealistic portraits that capture the characteristic features of a disorder while preserving patient privacy. Overall, the output from our approach holds promise for various applications, including visualizations for publications and educational materials and augmenting training data for deep learning.

11 January 2026 in Biomedicines
Verified
Journal Article
Open access
PDF file
MKMichaela Kuhlen
Michaela Kuhlen
FHFabio Hellmann
Fabio Hellmann
EPElisabeth Pfaehler
Elisabeth Pfaehler
EAElisabeth André
Elisabeth André
ARAntje Redlich
Antje Redlich
Artificial intelligence (AI) and machine learning (ML) are reshaping cancer research and care. In pediatric oncology, early evidence—most robust in imaging—suggests value for diagnosis, risk stratification, and assessment of treatment response. Pediatric endocrine tumors are rare and heterogeneous, including intra- and extra-adrenal paraganglioma (PGL), adrenocortical tumors (ACT), differentiated and medullary thyroid carcinoma (DTC/MTC), and gastroenteropancreatic neuroendocrine neoplasms (GEP-NEN). Here, we provide a pediatric-first, entity-structured synthesis of AI/ML applications in endocrine tumors, paired with a methods-for-clinicians primer and a pediatric endocrine tumor guardrails checklist mapped to contemporary reporting/evaluation standards. We also outline a realistic EU-anchored roadmap for translation that leverages existing infrastructures (EXPeRT, ERN PaedCan). We find promising—yet preliminary—signals for early non-remission/recurrence modeling in pediatric DTC and interpretable survival prediction in pediatric ACT. For PGL and GEP-NEN, evidence remains adult-led (biochemical ML screening scores; CT/PET radiomics for metastatic risk or peptide receptor radionuclide therapy response) and serves primarily as methodological scaffolding for pediatrics. Cross-cutting insights include the centrality of calibration and validation hierarchy and the current limits of explainability (radiomics texture semantics; saliency ≠ mechanism). Translation is constrained by small datasets, domain shift across age groups and sites, limited external validation, and evolving regulatory expectations. We close with pragmatic, clinically anchored steps—benchmarks, multi-site pediatric validation, genotype-aware evaluation, and equity monitoring—to accelerate safe, equitable adoption in pediatric endocrine oncology.

30 October 2025 in Orphanet Journal of Rare Diseases
Verified
Journal Article
Open access
PDF file
FHFabio Hellmann
Fabio Hellmann
IRInka Ristow
Inka Ristow
LWLennart Well
Lennart Well
SLSwanhild Lohse
Swanhild Lohse
MAMaxim Anokhin
Maxim Anokhin
AHAnja Harder
Anja Harder
Modern Artificial Intelligence (AI) has demonstrated its effectiveness by achieving human-level performance in various complex tasks, including the biomedical field. Cancer research, adapting to a fast-changing world, is leveraging AI as a promising framework to better understand tumor development. Moreover, current AI methods can help predict more suitable and personalized treatment strategies for specific types of tumors. We explored AI methods applied to Neurofibromatosis Type 1, focusing on glial tumors. Additionally, we have reviewed all publicly available datasets to date. Discussion of future challenges is highly desirable since Neurofibromatosis Type 1 is one of the most common hereditary tumor syndromes and is associated with an increased rate of glial tumors as well as a reduced life expectancy due to malignancy.

21 August 2024
Verified
Book Chapter
Closed access
PDF file
DSDominik Schiller
Dominik Schiller
SMSilvan Mertes
Silvan Mertes
MAMarcel Achzet
Marcel Achzet
FHFabio Hellmann
Fabio Hellmann
RSRuben Schlagowski
Ruben Schlagowski
EAElisabeth André
Elisabeth André

18 August 2026 in medRxiv
Verified
Preprint
Open access
PDF file
ALAnna Lutz
Anna Lutz
FHFabio Hellmann
Fabio Hellmann
EAElisabeth Andre
Elisabeth Andre
Heart failure (HF) affects over 64 million people worldwide and remains a leading cause of cardiovascular mortality. Early identification of patients at risk is essential for timely treatment and to support hospital and primary care physicians. This study compares XGBoost and a Transformer- based bidirectional cross-attention model using multimodal data to assess whether deep learning (DL) approaches can outperform classical machine learning (ML) methods for early HF prediction. We identified HF and non-HF patients from the MIMIC-IV database using ICD-9/10 codes, supplemented by clinical evidence from laboratory results, radiology, and discharge notes. Furthermore, we defined a 48-hour prediction window prior to the first clinical evidence of HF. Structured features were engineered from rolling-window statistics and clinical thresholds. Both XGBoost and Transformer models were trained on multimodal data and compared through an ablation study. Finally, we developed a dashboard using a small set of laboratory and medication features to deliver a 48- hour HF risk estimate, aiding clinician diagnosis. Multimodal models outperformed single-modality models across both architectures. The multimodal XGBoost model achieved the highest performance (F1 of 0. 8773 and PR-AUC of 0.9402), while the multimodal Transformer achieved slightly lower performance (F1 0.8635, PR-AUC 0.9209). Structured data contributed most to XGBoost (PR-AUC of 0.9163), whereas clinical notes were better captured by the Transformer (PR- AUC of 0.8220). Explainable dashboards further enhance transparency and usability by delivering quantitative 48-hour risk estimates from minimal features. This demonstrates, in this setting, that traditional ML can outperform DL models such as Transformers on tabular-dominated, multimodal clinical prediction tasks while preserving interpretability, underscoring decision-support systems potential to aid timely diagnosis.